Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries

By Nirmal Keshava. IEEE Transactions on Geoscience and Remote Sensing, 2004

383 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Artificial Intelligence, Media Technology

View Paper: https://www.semanticscholar.org/paper/092a2818c81504ad7fb6d3479272c344267f16fd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Qian Du
2. Xiuping Jia
3. Melba M. Crawford
4. Antonio J. Plaza
5. Weiwei Sun
6. He Yang
7. Javier Plaza
8. Bor-Chen Kuo

In Artificial Intelligence

1. Qian Du
2. Weiwei Sun
3. He Yang
4. Antonio J. Plaza
5. Xiuping Jia
6. Bor-Chen Kuo
7. Melba M. Crawford
8. Juan Mario Haut

In Media Technology

1. Qian Du
2. Antonio J. Plaza
3. Javier Plaza
4. Weiwei Sun
5. Juan Mario Haut
6. Mercedes Eugenia Paoletti
7. Xiuping Jia
8. He Yang

Citations in the corpus

• Feature Mining for Hyperspectral Image Classification (2013, methodology): “An iterative band add-on FS technique was also developed based on the spectral angle measure between two spectra from two classes, respectively, or the average between the spectra from two classes [46].”
• A Survey of Spectral Unmixing Algorithms (2003, methodology): “A more comprehensive treatment of the technical detail for each algorithm is available in other references [ 1 ].”
• Hyperspectral Band Selection: A Review (2019, methodology): “In [48], employing the exact decomposition of SAM, the band add-on (BAO) algorithm was presented to iteratively select bands that increase the angular separation between two spectra in a spectral library.”
• Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis (2008, methodology): “PCA and noise-adjusted PCA were proposed for unsupervised band selection in [1], distance-based measurement was investigated in [6], and information-theory-based band selection can be found in [7] and [8].”
• A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images (2012, neutral): “olution images [27]–[29]; 2) supervised classification and/or clustering of hyperspectral and multispectral images [30], [31]; 3) supervised CD [32]; 4) spectral unmixing [33], [34]; 5) target”
• Deep learning classifiers for hyperspectral imaging: A review (2019, background): “…the evidential reasoning -ER- (Sanz, 2001)), from spectral-based methodologies (traditional distance metrics based classifiers (Du and Chang, 2001; Keshava, 2004), spectral angle mapper -SAM- (Camps-Valls, 2016; Calin et al., 2018), etc.) to spatial or spectral-spatial ones (sparse coding…”
• Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking (2016, background): “In order to make a good compromise, the salient bands from the entire hyperspectral volume should be selected, extracting the most informative clues and abandoning the less important ones [10].”